| Paper ID | D-2-1.6 |
| Paper Title |
CELL OUTAGE DETECTION USING DEEP CONVOLUTIONAL AUTOENCODER IN MOBILE COMMUNICATION NETWORKS |
| Authors |
Yeh-Hong Ping, Po-Chiang Lin, Yuan Ze University, Taiwan |
| Session |
D-2-1: Digital Convergence of 5G, AIoT and Security I |
| Time | Wednesday, 09 December, 12:30 - 14:00 |
| Presentation Time: | Wednesday, 09 December, 13:45 - 14:00 Check your Time Zone |
|
All times are in New Zealand Time (UTC +13) |
| Topic |
Wireless Communications and Networking (WCN): Special Session: Digital Convergence of 5G, AIoT and Security |
| Abstract |
The cell outage detection is an important issue of the self-organizing networks defined by the 3GPP. The objective of the cell outage detection is to determine whether these exists any cell outage in mobile communication networks. The cell outage detection problem is important in next generation mobile communication networks due to the increasing number of base stations. Using machine learning techniques to detect the cell outage would be promising. However, the data imbalance and the users’ privacy issues make the machine learning based cell outage detection more challenging. In this paper, we propose a cell outage detection method using the deep convolutional autoencoder, which is an unsupervised learning approach. We formulate the cell outage detection problem as an anomaly detection problem. The proposed method could solve this anomaly detection problem by using the normal measurement data only. The proposed method does not rely on the cell outage data and the location information of users. Comprehensive system-level simulations validate the performance of the proposed method. |